Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add pwdev-solucoes/pwdev-claude-marketplace --skill power-tddgit clone --depth 1 https://github.com/pwdev-solucoes/pwdev-claude-marketplaceWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/pwdev-solucoes/pwdev-claude-marketplace/power-tdd)<a href="https://agentmods.dev/skills/pwdev-solucoes/pwdev-claude-marketplace/power-tdd"><img src="https://agentmods.dev/badge/skills/pwdev-solucoes/pwdev-claude-marketplace/power-tdd/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/pwdev-solucoes/pwdev-claude-marketplace/power-tdd"><img src="https://agentmods.dev/badge/skills/pwdev-solucoes/pwdev-claude-marketplace/power-tdd.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00018 | $0.00704 |
| Opus 5 | $0.00009 | $0.00352 |
| Sonnet 5 | $0.00004 | $0.00141 |
| Haiku 4.5 | $0.00002 | $0.00070 |
Grade A, and why
power-tdd scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Test First
The iron law
No production code without a failing test first.
Not "usually". Not "unless it's small". The rule has no exception clause, because every exception anyone has proposed was a case where the test was skipped and the bug shipped.
The cycle
RED — write one failing test
One test, for one behavior, with a name that says what the behavior is. Use real code, not mocks of the thing you are testing. A mock of your own function tests that you can configure a mock.
Before you write it, name the production change that would make this test fail. If you cannot name it, you do not yet know what you are testing.
Verify RED — mandatory
Run it. Watch it fail. Then check why it failed:
- It must fail, not error. An import error is not a red test.
- It must fail because the behavior is missing, not because of a typo, a missing fixture, or a wrong path.
- If it passes, you are testing behavior that already exists. Stop and find the real gap.
Skipping this step is where the whole cycle stops working, because a test that never failed proves nothing when it passes.
GREEN — the minimum
Write the least code that makes it pass. No speculative parameters, no "we'll need this later", no configuration for a case nobody asked for.
Verify GREEN
Run it and watch it pass. Then run the surrounding suite: your change must not have broken anything. Read the output — not the exit code alone.
REFACTOR — only on green
Improve names and structure with the tests passing. Run them again after.
If you wrote code first
Delete it. Do not keep it in a scratch file, do not adapt it, do not look at it while writing the test. Code you can see is code the test will be shaped to fit, which produces a test that passes for the wrong reason.
Rationalizations
| Thought | Reality |
|---|---|
| "It's a one-line change" | One-line changes ship bugs. That is why they are worth a test. |
| "I'll add the test after" | The test after is shaped by the code. It tests what you built, not what was needed. |
| "It's just a config value" | If a wrong value breaks things, a test can catch a wrong value. |
| "There's no framework here" | Then the first task is the framework, and it is a real task. |
| "I already know it works" | Then the test passes immediately and costs a minute. Write it. |
| "The test would be trivial" | Trivial tests catch typos, which are the most common defect. |
| "This is exploratory" | Exploration is a spike, and its code is throwaway. Label it and delete it. |
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 7d ago First seen · 75 lines · 18 tokens per session scan A bf68e2af4807
power-tdd is a skill published in the GitHub repository pwdev-solucoes/pwdev-claude-marketplace (2 stars, last pushed today), licensed Apache-2.0. It adds 18 tokens to every session and 704 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
engram-testing-coverage
TDD and coverage standards for Engram. Trigger: When implementing behavior changes in any package.
iterative-development
TDD iteration loops using Claude Code Stop hooks - runs tests after each response, feeds failures back automatically.
python
Python development with ruff, mypy, pytest - TDD and type safety.
nw-fp-clojure
Clojure language-specific patterns, data-first modeling, REPL-driven development, and spec.
strict-tdd
Strict RED->GREEN->REFACTOR test-driven development with enforcement. Never write production code before a failing test. Atomic commits per TDD cycle.
mobiai-mobile-tdd
You MUST use this before writing any implementation code for a mobile feature, bug fix, refactor, or behavior change. Tests come before implementation — no exceptions.